156 citations · 191 across the 13 of their papers we have counts for
14 papers
VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion
Aastha Sharma, Guangjing Wang
Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech that differs from the generators represented in many legacy spoofing benchmarks. T…
Learning to Evade: Adaptive Attacks on Audio Watermarking
Weikang Ding, Hanqing Guo, Rui Duan +4
Advances in generative audio have intensified copyright concerns, making audio watermarking increasingly important for asserting ownership. However, existing audio watermarking met…
ClearMask: Noise-Free and Naturalness-Preserving Protection Against Voice Deepfake Attacks
Yuanda Wang, Bocheng Chen, Hanqing Guo +3
Voice deepfake attacks, which artificially impersonate human speech for malicious purposes, have emerged as a severe threat. Existing defenses typically inject noise into human spe…
Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving
Ce Zhou, Qiben Yan, Daniel Kent +4
Monocular Depth Estimation (MDE) is a pivotal component of vision-based Autonomous Driving (AD) systems, enabling vehicles to estimate the depth of surrounding objects using a sing…
Decoding Emotions: Unveiling Facial Expressions through Acoustic Sensing with Contrastive Attention
Guangjing Wang, Juexing Wang, Ce Zhou +4
Expression recognition holds great promise for applications such as content recommendation and mental healthcare by accurately detecting users' emotional states. Traditional method…
Optical Lens Attack on Deep Learning Based Monocular Depth Estimation
Ce Zhou, Qiben Yan, Daniel Kent +3
Monocular Depth Estimation (MDE) plays a crucial role in vision-based Autonomous Driving (AD) systems. It utilizes a single-camera image to determine the depth of objects, facilita…
Protecting Activity Sensing Data Privacy Using Hierarchical Information Dissociation
Guangjing Wang, Hanqing Guo, Yuanda Wang +3
Smartphones and wearable devices have been integrated into our daily lives, offering personalized services. However, many apps become overprivileged as their collected sensing data…
The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs
Bocheng Chen, Hanqing Guo, Guangjing Wang +2
Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using huma…
Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems
Guangjing Wang, Ce Zhou, Yuanda Wang +3
Transferable attacks allow adversarial manipulations or learned attack mechanisms constructed in one setting to compromise other AI systems, potentially reducing attack costs and a…
PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection
Hanqing Guo, Guangjing Wang, Yuanda Wang +3
In this paper, we propose PhantomSound, a query-efficient black-box attack toward voice assistants. Existing black-box adversarial attacks on voice assistants either apply substitu…
DynamicFL: Balancing Communication Dynamics and Client Manipulation for Federated Learning
Bocheng Chen, Nikolay Ivanov, Guangjing Wang +1
Federated Learning (FL) is a distributed machine learning (ML) paradigm, aiming to train a global model by exploiting the decentralized data across millions of edge devices. Compar…
Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots
Bocheng Chen, Guangjing Wang, Hanqing Guo +2
Recent advances in natural language processing and machine learning have led to the development of chatbot models, such as ChatGPT, that can engage in conversational dialogue with…
VSMask: Defending Against Voice Synthesis Attack via Real-Time Predictive Perturbation
Yuanda Wang, Hanqing Guo, Guangjing Wang +2
Deep learning based voice synthesis technology generates artificial human-like speeches, which has been used in deepfakes or identity theft attacks. Existing defense mechanisms inj…
A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT
Ce Zhou, Qian Li, Chen Li +16
Pretrained Foundation Models (PFMs) are regarded as the foundation for various downstream tasks with different data modalities. A PFM (e.g., BERT, ChatGPT, and GPT-4) is trained on…